[New feature] A Noise Injection Method for Flux

### New Feature for FluxPipeline
Paper: [Link](https://openreview.net/pdf?id=KzokzKV4JK)
Code : [Link](https://anonymous.4open.science/r/SSNI-F746/README.md)
workflow : [Link](https://www.dropbox.com/scl/fi/hhitjx6lqpqpv8xjx9ikq/Flux-Noise-Injection.json?rlkey=45xnu45j1i5owiwhc7z1hppn1&e=1&dl=0)
This paper introduces Sample-specific Score-aware Noise Injection (SSNI) to improve diffusion-based purification (DBP) methods. Unlike existing approaches that use a fixed noise level (t*) for all samples, SSNI adapts t* based on how noisy or clean each sample is. Using a pre-trained score network, SSNI estimates a sample's deviation from the clean data and adjusts the noise level accordingly.

This have stunning Results with Flux


@sayakpaul @yiyixuxu

Start with FluxPipeline and read the linked paper, reference implementation, and workflow to understand the proposed SSNI method. Done would be an integrated noise-injection feature for Flux with validation against the behavior and results described in the issue.

Scritto dal modello di indicizzazione a partire dal testo della issue.